Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    "

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    瞬
    -0.08
     tale
    -0.07
    �
    -0.07
    党员干部
    -0.07
     Tech
    -0.06
    Shield
    -0.06
     firstname
    -0.06
    Ps
    -0.06
    时任
    -0.06
    Ȓ
    -0.06
    POSITIVE LOGITS
    无穷
    0.07
    的状态
    0.07
     Interval
    0.07
    ubectl
    0.06
     entfer
    0.06
    ><!--
    0.06
     agreed
    0.06
     rolling
    0.06
     Retirement
    0.06
     French
    0.06
    Act Density 0.002%

    No Known Activations